ComfyUI Node
Scenema VAE Encode (voice reference) ⚡
Encode a voice reference clip to an audio latent for Scenema generation.
Scenema VAE Encode (voice reference) ⚡
- vae
- audio
- ref_latent
◄max_seconds20.0►
Category🤖 CCTech/Scenema
Inputs (3)
| Name | Type | Default | Description |
|---|---|---|---|
| vae | VAE | — | |
| audio | AUDIO | — | |
| max_secondsopt | FLOAT | 20.01–20 | Seconds of reference audio to encode. Hard-capped at 20s. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| ref_latent | LATENT | — |